Papers › Exploring the Jungle of Bias: Political Bias Attribution in Language Models via...

Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis

15 Nov 2023arXiv:2311.08605archive 2025-07-28

David F. Jenny, Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin

The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both results on debiasing methods in the literature and reports of alignment-related defects from the wider community, bias remains a poorly understood topic despite its practical relevance. To enhance the understanding of the internal causes of bias, we analyse LLM bias through the lens of causal fairness analysis, which enables us to both comprehend the origins of bias and reason about its downstream consequences and mitigation. To operationalize this framework, we propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the LLM decision process. By applying Activity Dependency Networks (ADNs), we then analyse how these attributes influence an LLM's decision process. We apply our method to LLM ratings of argument quality in political debates. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment, and discuss the consequences of our findings for human-AI alignment and bias mitigation. Our code and data are at https://github.com/david-jenny/LLM-Political-Study.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

david-jenny/llm-political-study officialmentioned in papermentioned on GitHubMITSyntology: 15 samples, 11 ran (0 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
4unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from david-jenny/llm-political-study. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

david-jenny/llm-political-study official repository 15 samples, 11 ran (0 instrument-failed) · 4 unverified
compute_distance_metrics utils/network_utils.py ran MIT (permissive) · 5bffff3cb2fb4b88 · report fixture: signature c_xy:DataFrame/0/?, pc_xyz:ndarray/3/float, flip_sign:bool/0/bool · returned ndarray · level recorded 2026-09-24
compute_node_activity_and_pcpn utils/network_utils.py ran MIT (permissive) · 9a9e3ce0a7cf2f30 · report fixture: signature c_xy:DataFrame/0/?, d_xyz:ndarray/3/float, weight_by_correlation_to_others:bool/0/bool · returned tuple · level recorded 2026-09-24
compute_partial_correlations utils/network_utils.py ran MIT (permissive) · 572b4d90507e8119 · report fixture: signature c_xy:DataFrame/0/?, flip_sign:bool/0/bool · returned ndarray · level recorded 2026-09-24
create_speaker_df utils/plotter_utils.py ran MIT (permissive) · b72f26a8ac91386c · report fixture: signature slice_speaker_base_observables:dict/0/?, slice_speaker_observables:dict/0/? · returned DataFrame · level recorded 2026-09-24
gen_bootstrap_data utils/statistical_test_utils.py ran MIT (permissive) · 9b2f0a8e0c9cc1a4 · report fixture: signature data:ndarray/2/int, n:int/0/int · returned ndarray · level recorded 2026-09-24
gen_subset_data utils/statistical_test_utils.py ran MIT (permissive) · 1edc977e616f8ecc · report fixture: signature data:ndarray/2/int, n:int/0/int · returned ndarray · level recorded 2026-09-24
get_slice_contextual_variables datasets/llm_measurements/query_llm.py ran MIT (permissive) · 651ae257712c7c1b · report fixture: signature slices_d:dict/0/?, slice_id:str/0/str · returned dict · level recorded 2026-09-24
get_slice_metadata datasets/llm_measurements/query_llm.py ran MIT (permissive) · a8ea4c06a5fba55d · report fixture: signature slices_d:dict/0/?, slice_id:str/0/str · returned dict · level recorded 2026-09-24
get_speaker_metadata datasets/llm_measurements/query_llm.py ran MIT (permissive) · 99a2a61c0258d6cc · report fixture: signature slices_d:dict/0/?, slice_id:str/0/str, speaker:str/0/str · returned dict · level recorded 2026-09-24
std in 5 papers utils/statistical_test_utils.py ran fingerprinted MIT (permissive) · 2bc5a8a09a4696f8 · report fixture: signature data:ndarray/1/float · returned float64 · level recorded 2026-09-24
transform_str_categories_to_flags utils/plotter_utils.py ran MIT (permissive) · 309d6c16f18bf747 · report fixture: signature df:DataFrame/0/?, column_name:str/0/str · returned DataFrame · level recorded 2026-09-24
detokenizer datasets/cpd_debates/cpd_debate_scraper.py unverified MIT (permissive) · 51fcdc53b4801135 · report
encoding_getter datasets/cpd_debates/cpd_debate_scraper.py unverified MIT (permissive) · e50b8f5c380e0ce4 · report
load_slice_and_measured_observables utils/plotter_utils.py unverified MIT (permissive) · 6496089f2dd2deb1 · report
tokenizer datasets/cpd_debates/cpd_debate_scraper.py unverified MIT (permissive) · 957d76c0f71ca73e · report

Tasks

Decision MakingFairness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections